© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7142
    Prev
    Next
    INDEX
    Explanations

    to choose from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elves
    -0.09
     EXPRESS
    -0.09
     medi
    -0.09
    à¸ĸ
    -0.08
     ded
    -0.08
    Ìģ
    -0.08
    unga
    -0.08
    admin
    -0.08
     expires
    -0.08
    ungle
    -0.08
    POSITIVE LOGITS
     suit
    0.24
     cater
    0.18
     Suit
    0.18
     help
    0.18
     accommodate
    0.15
     ensure
    0.15
     rival
    0.14
     suits
    0.14
    suit
    0.13
     satisfy
    0.12
    Activations Density 0.082%

    No Known Activations